© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18939
    Prev
    Next
    INDEX
    Explanations

    coordinator structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĿ¢å¯¹
    -0.07
    æľ«
    -0.07
    ä¸įçŁ¥éģĵ为ä»Ģä¹Ī
    -0.07
     rapp
    -0.07
     muka
    -0.06
    äºİæĺ¯åľ¨
    -0.06
     Comer
    -0.06
    kana
    -0.06
    åıªä»£è¡¨
    -0.06
    ff
    -0.06
    POSITIVE LOGITS
     overarching
    0.09
     overall
    0.09
    overall
    0.08
    agne
    0.08
    plevel
    0.08
    æķ´ä½ĵçļĦ
    0.08
    æķ´ä½ĵä¸Ĭ
    0.08
    çļĦæĢ»ä½ĵ
    0.08
    çļĦæķ´ä½ĵ
    0.08
    æķ´ä½ĵ
    0.08
    Activations Density 0.648%

    No Known Activations